Abstract
In this paper, we discuss the problem of how human control strategy can be represented as a parametric model using a support vector machine (SVM) and how an SVM-based controller can be used in controlling dynamically stable systems. The SVM approach has been implemented in the balance control of Gyrover, which is a dynamically stable, statically unstable, single-wheel mobile robot. The experimental results that compare SVM with general artificial neural network approaches clearly demonstrate the superiority of the SVM approach with regard to human control strategy learning.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Montgomery, J.F., Bekey, G.A.: Learning helicopter control through “teaching by showing.” In: Proc. IEEE Int. Conf. on Decision and Control, vol. 4, pp. 3647–3652. IEEE, Piscataway (1998)
Yang, J., Xu, Y., Chen, C.S.: Hidden Markov model approach to skill learning and its application to telerobotics. IEEE Trans. Robot. Autom. 10(5), 621–631 (1994)
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)
Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)
Bernhard, S., Burges, C.J.C., Smola, A.: Advanced in Kernel Methods Support Vector Learning. MIT, Cambridge (1998)
Sebald, D.J., Buckle, J.A.: Support vector machine techniques for nonlinear equalization. IEEE Trans. Signal Process. 48, 3217–3226 (2000)
Trafalis, T.B., Ince, H.: Support vector machine for regression and applications to financial forecasting. In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on, vol. 6, pp. 348–353. IEEE, Piscataway (2000)
Arimoto, S., Kawamura, S., Miyazaki, F.: Bettering operation of robots by learning. J. Robot. Syst. 1(2), 123–140 (1984)
Craig, J.J.: Learning control of manipulators through repeated trails. In: Proc. American Control Conference, pp. 1566–1574, San Diego, June 1984
Aboaf, E.W.: Task-level robot learning. Masters thesis, Massachusetts Institute of Technology, August (1988)
Nechyba, M.C., Xu, Y.: Stochastic similarity for validating human control strategy models. IEEE Trans. Robot. Autom. 14(3) 437–451 (1998)
Xu, Y., Song, J., Nechyba, M.C., Yam, Y.: Performance evaluation and optimization of human control strategy. IEEE J. Robot. Autom. 965, 1–18 (2002)
Nechyba, M.C, Xu, Y.: On discontinuous human control strategies. Int. J. Intell. Syst. 16(4) 547–570 (2001)
Nechyba, M.C., Xu, Y.: Learning and transfer of human real-time control strategy. J. Adv. Comput. Intell. 1(2), 137–154 (1997)
Yang, J., Xu, Y., Chen, C.S.: Human action learning via hidden Markov model. IEEE Trans. Syst. Man Cybern. 27(1), 34–44 (1997)
Burges, C.J.C., Scholkopf, B.: Improving the accuracy and speed of support vector learning machines. In: Mozer, M., Jordan, M., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, pp. 375–381. MIT, Cambridge (1997)
Yang, S.X.: Neural dynamics and computation for real-time map building and path planning of mobile robots. Dyn. Contin. Discrete Impuls. Syst. B 1(10), 1–17 (2003)
Yang, S.X., Hu, T.: An efficient neural network approach to real-time control of a mobile robot with unknown dynamics. Differ. Equ. Dyn. Syst. 10(2), 151–168 (2002)
Antsaklis, P.J. (guest ed.): Special issue on neural networks in control systems. IEEE Control Syst. Mag. 12(2), 8–57 (1992)
Smola, A.: General cost function for support vector regression. In: Proceedings of the Ninth Australian Conf. on Neural Networks, pp. 79–83, Brisbane, 11–13 February 1998
Nechyba, M., Xu, Y.: Cascade neural networks with node-decoupled extended kalman filtering. In: Proc. IEEE Int. Symp. on Computational Intelligence in Robotics and Automation, vol. 1, pp. 214–219. IEEE, Piscataway (1997)
Nechyba, M.: Learning and validation of human control strategy. Ph.D. thesis, Carnegie Melon University (1998)
Xu, Y., Yu, W., Au, K.: Modeling human control strategy in a dynamically stabilized robot. In: Proc. of the 1999 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, vol. 2, pp. 507–512. IEEE, Piscataway (1999)
Lee, K.K., Xu, Y.: Human sensation modeling in virtual environments. In: Proc. of 2000 IEEE/RSJ Internation Conference on Intelligent Robots and Systems, vol. 1, pp. 151–156. IEEE, Piscataway (2000)
Brown, H.B., Xu, Y.: A single wheel gyroscopically stabilized robot. In: Proc. IEEE Int. Conf. on Robotics and Automation, vol. 4, pp. 3658–3663. IEEE, Piscataway (1996)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ou, Y., Qian, H. & Xu, Y. Support Vector Machine Based Approach for Abstracting Human Control Strategy in Controlling Dynamically Stable Robots. J Intell Robot Syst 55, 39–54 (2009). https://doi.org/10.1007/s10846-008-9292-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-008-9292-8